Face recognition method based on HOG feature and SVM multi-classifier

A multi-classifier, face recognition technology, applied in the field of image processing, can solve the problem of multi-classification problem, which is not effective, can only judge whether it is A or B, etc., to improve recognition accuracy, reduce shadows and lighting changes, solve poor effect

Inactive Publication Date: 2017-08-18
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, SVM can generally only be used for binary classification problems, that is, it can only judge the situation of either A or B, and it is not effective for multi-classification problems.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Face recognition method based on HOG feature and SVM multi-classifier
  • Face recognition method based on HOG feature and SVM multi-classifier
  • Face recognition method based on HOG feature and SVM multi-classifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The specific embodiment of the face recognition method based on HOG feature and SVM multi-classifier used in the present invention will be described in more detail below.

[0045] According to attached figure 1 The flow chart corresponding to the face recognition method based on HOG features and SVM multi-classifier is shown, with figure 2 An example of a face image matrix is ​​shown, with image 3 Shown SVM classifier training example figure, the embodiment of the present invention is (as figure 1 shown):

[0046] 1) The image matrix obtained after the input image is grayscaled is as follows: figure 2 shown. right figure 2 The matrix obtained after normalizing each pixel value in is:

[0047]

[0048] 2) Perform Gamma (gamma) correction on the image matrix G obtained after normalization, take gamma=0.5, calculate G'(x,y)=G(x for each pixel value G(x,y) in G ,y) gamma . The image matrix after Gamma correction is as follows:

[0049]

[0050] 3) Calcul...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a face recognition method based on a HOG feature and a SVM multi-classifier. The method comprises training the SVM multi-classifier by calculating and counting the feature formed by a HOG of the local area of a face image, and recognizing a sample image in a way of voting in pairs. A type with the most votes is the recognition result of the sample. The method achieves a high recognition rate while guaranteeing low time complexity.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a face recognition method based on HOG (Histogram of Oriented Gradient, histogram of oriented gradient) features and SVM (Support Vector Machine, support vector machine) multiple classifiers. Background technique [0002] Image processing technology refers to a technology that uses computers to analyze and process images, reduce the factors that affect the analysis results in images, and extract the required information. It includes image enhancement and restoration, image transformation, segmentation and compression, etc., generally refers to digital images. deal with. A digital image refers to a large two-dimensional array obtained by shooting with a shooting device. The elements of the array are called pixels, and their values ​​are called grayscale values. Using image compression technology, the two-dimensional pixel array can be represented by one-dimensional featu...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46
CPCG06V40/173G06V10/507
Inventor 冯文廷陈志岳文静李国翔徐鹏
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap